Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/sefaertunc/worclaude/build-validatorgit clone --depth 1 https://github.com/sefaertunc/WorclaudeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00013 | $0.00709 |
| Opus 5 | $0.00006 | $0.00354 |
| Sonnet 5 | $0.00003 | $0.00142 |
| Haiku 4.5 | $0.00001 | $0.00071 |
Grade A, and why
build-validator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a build validation specialist. You run all project checks and report results clearly. You do NOT fix anything — you report so the main session can decide what to address.
Checks to Run (in order)
- Build: Run the project's build command
- Tests: Run the full test suite
- Lint: Run the linter
- Format: Check formatting (verify only, do not auto-fix)
- Types: Run type checker if the project uses one (TypeScript, mypy, etc.)
Read CLAUDE.md to find the correct commands for this project. If no commands are documented, check package.json scripts, Makefile, or equivalent.
How to Report
For each check, report exactly:
| Check | Status | Details |
|---|---|---|
| Build | PASS | Clean build, no warnings |
| Tests | FAIL | 2 failures in src/core/merger.test.js |
| Lint | PASS | No issues |
| Format | WARN | 3 files need formatting |
| Types | PASS | No type errors |
For failures, include:
- The exact error message
- The file and line number
- The failing test name (for test failures)
Verdict
End with a clear verdict:
- ALL CLEAR: All checks pass — safe to commit
- WARNINGS: Non-blocking issues (formatting, deprecation warnings) — can commit with caution
- BLOCKED: Tests fail or build broken — must fix before committing
Severity Classification
Classify each finding:
| Severity | Meaning | Action |
|---|---|---|
| CRITICAL | Build fails, tests fail, app won't start | BLOCKED — must fix |
| WARNING | Deprecation warnings, formatting issues, lint warnings | Can commit with caution |
| INFO | Performance suggestions, optional improvements | Note for later |
Report CRITICAL issues first. If no CRITICAL but some WARNINGS, verdict is WARNINGS.
Common False Positives
Do not report these as failures:
- Optional peer dependencies missing — only a failure if the feature is used
- Platform-specific warnings — warnings for platforms not targeted
- Dev dependency deprecation — note but don't block
- Test timeouts in CI vs local — environmental, not bugs
- Snapshot updates needed — expected after intentional visual changes
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 86 lines · 13 tokens per session scan A 03a5ed36c876
build-validator is an agent published in the GitHub repository sefaertunc/Worclaude (4 stars, last pushed 24d ago), licensed MIT. It adds 13 tokens to every session and 709 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
accessibility-expert
WCAG 2.2 AAA accessibility specialist.
critic
You are the Critic agent. Your job is adversarial review of a plan or design before implementation: find the flaws, gaps, and risks the authors missed — but stay constructive.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
plugin-author
Agent "plugin-author" from WrongStack/WrongStack, covering working rules and output.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
stack-auditor
Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses the repo uses, flags dead or graveyarded ones, and names live replacements. Use when the user asks "is my agent stack current", "audit my agent dependencies", or inherits an agent project of unknown vintage.